Senior Staff Software Engineer, Behaviors

We're Cruise, a self-driving service designed for the cities we love.

We’re building the world’s most advanced self-driving vehicles to safely connect people to the places, things, and experiences they care about. We believe self-driving vehicles will help save lives, reshape cities, give back time in transit, and restore freedom of movement for many.

In our cars, you’re free to be yourself. It’s the same here at Cruise. We’re creating a culture that values the experiences and contributions of all of the unique individuals who collectively make up Cruise, so that every employee can do their best work. 

Cruise is committed to building a diverse, equitable, and inclusive environment, both in our workplace and in our products. If you are looking to play a part in making a positive impact in the world by advancing the revolutionary work of self-driving cars, come join us. Even if you might not meet every requirement, we strongly encourage you to apply. You might just be the right candidate for us.

The Behavior Foundations team is responsible for building and scaling the foundational technologies across ML infrastructure/framework, training and evaluation pipelines/workflows, data mining, learning algorithms, diagnosis, monitoring, testing and metrics. This foundation is supporting our researchers and engineers across Behaviors org to solve the most critical problems on Autonomous Vehicle (AV) decision tasks such as:

• Building a globally consistent prediction of what all different nearby agents (like other cars, buses, animals, pedestrians) are going to in the next few seconds;
• Generating safe, comfortable and feasible trajectories to navigate dynamic urban environments;
• Scoring and selecting the optimal trajectory, optimizing across many dimensions such as safety, comfort and customer experience.

As Cruise’s business continues to scale rapidly, it’s critical to build a stable, reliable, scalable, flexible and cost-efficient foundation and long term architecture. We work closely with our partner teams across Cruise AI to lay out this foundation with a vision of building a Continuous Learning Machine, Data-Centric AI and objective model performance evaluation, to automate and accelerate our machine learning development, testing, and deployment and continuously ship models to improve the behaviors in our AVs, enabling our AVs to drive safely, reliably and smoothly in all different cities and scenarios.

What you’ll be doing:

• Design and implement shared infrastructure and tooling among the Behaviors teams. Identify opportunities to unify approaches and increase developer velocity.
• From a research perspective, exploring, prototyping, validating, and iterating new algorithms.
• On the development side, driving efforts to optimize, supervise and refine on-road performance for models on the path to production.
• Identify opportunities to accelerate the training and evaluation process of behavior changes to the vehicle. Build training framework, data infra and metrics pipelines to accelerate the training and feedback loop on AI projects.
• Own the quality of the development and ensure the solutions are scalable, secure, and optimized for user experience and performance. Raise the bar on engineering excellence by producing best in class of code, documentation, testing, and monitoring.
• Own technical projects from start to finish and be responsible for major technical decisions and tradeoffs. Effectively participate in team’s planning, code reviews and design discussions.
• Consider the effects of projects across multiple teams and proactively manage conflicts. Work closely with partner teams to ensure they are benefiting from the systems we built.

What you must have:

• Strong experience with C, C++ or Python.
• 8+ years of experience in machine learning and classification
• Extensive experience with ML frameworks such as Tensorflow, Caffe, and PyTorch
• Excellent mathematical reasoning skills, especially with probability
• Strong understanding of code efficiency/performance and reliability
• Outstanding ability to write clean, fast, reliable, and highly scalable software
• Experience building, deploying, and operating production-level high-availability full-stack services
• Passionate about self-driving technology and its potential impact on the world
• BS, MS or PhD in CS, Math, or equivalent real-world experience
• Strong organization and communication to work well across teams in a fast-paced environment

Bonus points!

• Experience with ROS, OpenCV, Gazebo, or PCL
• Even better if you understand: parallel training, active learning, model deployment (e.g., TensorRT conversion)
• Experience with build s